Weekly Update for October 1

# Weekly Update for October 1
### 2018/10/01

---

---
class: primary 
# New CSAFE slide template

We're now using [`xaringan`](https://github.com/yihui/xaringan)

What's changed:

- New person slide:

````
---
class: inverse
# Your Name
````

---
class: secondary

- New content slide with title:

````
---
class: primary
# Title of slide

Slide content
````

- New content slide without title:

````
---
class: secondary

Slide content with no title on slide
````

---
class: inverse
# Sample User

---
class: primary
# Sample Slide

- Sample Table. Sam Tyner talked about the three must-haves of your summary:

---
class: secondary

- If you are going to add an image, **create a directory** with your name within "images" folder. For example, "images/**guillermo**/sample_image.JPG"

---
class: inverse
# Sam

---
class: primary
# Update on plans:

- submit papers from thesis for publication
    + **Chapter 1 ready to submit this week**
    + Chapter 2 up next
- writing R packages with SP
    + glass 
    + shoes
    + "uncertainty pyramid" stuff with SL & HI
- **Glass EDA paper** with SP. **Poster at Forensics@NIST**  
- working on book funded by ROpenSci Fellowship 
- ~~narrowing down topics & formats for new CSAFE training materials~~ **Preparing talk for Albany State University's Forensic Science week next week (!)**
- writing "Ten Simple Rules for..." articles with DO
    + statisticians doing forensic science
    + forensic scientists doing statistics
    + [legal professionals encountering statistics](https://github.com/CSAFE-ISU/slides/issues/2)
    
---
class: primary
# PCA on Glass data

Variable loadings: variables near each other are correlated

![](images/sam/pca_loadings_glass.png)

---
class: primary
# Var. Imp. Mfr A

---
class: inverse
# Guillermo

---
class: secondary

- Finish package to check format of files from database
    - checksum table included?

- Study papers on pressure differences
    1. Separate shoe by areas?
    1. Normalize shoes?
    1. 1 and 2 would imply to align (but we have low resolution)

---
class: inverse
# James

---
class: primary
# Currently

* Science Bound Saturday
   + 24 High School Students, many interested in Forensics
   + One very interested in forensics and statistics 
   + Lots of great questions
   
* Developed the 3D written procedure specifically for mud and dirt prints

* Ironed out what images will be taken

* Started 3D scanning shoes that do not have complete sets (50 pairs)
---
class: primary
# Cart

* Data Collection on Hold
 + Consistency in Photographs - building a rolling camera cart
 
 
<img src = "images/James/Cart.png" width="60%"/>

---
class: inverse
# Soyoung

---
class: primary
# Fall semester plans: 
 - Shoes
    + Wrap up shoe analysis using edges and SURF 
    + Compare the performance with other methods such as phase only correlations, Fourier-Mellin transformation correlation
    + Do analysis with CSAFE shoe data
    + Submit papers regarding shoe analysis soon!
   
- Research on "uncertainty pyramid" with Steve and Hari at NIST   
 - Glass analysis with Sam
    + Exploratory analysis 
    + Various covariance estimations
    + Submit papers!
   
- Working on book chapters of glass and shoes funded by ROpenSci Fellowship

---
class: primary
# Analysis result with CSAFE shoe data 
- All nike shoes with size of 8.5 and 10.5 at time 4 (6 months)
- KM (210) : Between replicates within IDs
- KNM (180) : Between IDs
- Methods : Edge matching with three circles and RF for score, phase-only correlation (POC), Fourier-Mellin transform correlation (FMTC)
 <img src="images/soyoung/RF_POC_FMTC_plot.PNG" width="60%">

---
class: inverse
# Amy

---
class: primary
# Fall Semester Goals

- **Data Collection** Things are happening.
- Expand Bayesian hierarchical model
 - **Formal Model Selection** Still focused here.
 - Tests and Intervals
 - Validation
- Write and submit a paper on that modeling.
- Exploritory analysis of 'next level' features (AAFS)
 - **Work with Ben and Nick** 
 - FlashID data - this week?
 - Re-extract data & re-run models
 
---
class: inverse
# Ben

---
class: primary
# Semester Intentions
<img src = "images/ben/stack.jpg" width="35%"/>
- Collaborate w/Nic & Amy to improve handwriting project
- Develop improvements / features part of algorithm
- Eventually port algorithm through an application portal
- Improve file structure of project
- Working on preprocessing binary image
 - Prototyping w/ Numba & Python
 - Testing performance relative to Cpp
 - Hope to expedite development

---
class: inverse
# Nick

---

![](images/Nick/RealNodeCounts.png)

---
class: secondary
# Flash ID 4 Node Grapheme

- This is a good 4 node grapheme. We would like to do this.

---
class: secondary
# Flash ID 4 Node Grapheme

- This is a bad 4 node grapheme. We would NOT like to do this.

---
class: inverse
# Nate

---
class: primary
# Groove ID

---
class: secondary

<img src = "images/Nate/results_comparison_hamby44_zoom.png" width="100%" height="100%"/>
 
---
class: secondary

---
class: secondary

---
class: secondary

---
class: inverse
# Kiegan

---
class: primary   
# Fall Semester Goals

- Submit to AFTE journal  
- Complete writing of Chapman & Hall book  
- **Write a joint paper with Nate on grooves project**  
    - Outline ready to go  
    - Starting "bake-off" and writing soon  
- Data structure issue

---
class: primary  
# Data structure issue  
![](images/kiegan/median_hamby.png)

---
class: primary  
# Data structure issue  
![](images/kiegan/median_houston.png)

---
class: inverse
# Danica

---
class: primary   
# Fall Semester Update

- Submit BF vs. LR paper to AOS 
    - Done!  
- Write a follow-up paper to LPR  
    - working on making second draft less technical
- Continue NIJ grant to validate FDE conclusions  
    - received survey results from pilot set of examiners
    - starting to look at kinematic/dynamic scores
    - can use these to recreate the static scans
- New NIJ grant awarded!
    - Co-PI with Larry Tang from NIST/GMU
    - 1 yr. = approx. $200,000
    - error rates
    - conclusion scales

---
class: inverse
# Susan

---
class: primary
# Sorry I can't be there today!

Last week, I worked on:

- Debugging picture labeling for Neural Network, working through model issues
- Relabeling pictures (manual tagging)
- Bullet resampling - package works, needs to be faster
- Pestering IT about the Shoe Database frontend (sigh)
- (w/ Nick) Handwriting methods applied to fingerprints - not bad, but picture quality issues

This week:

- More debugging of NN model
 - Refactor bullet resampling package
 - More fingerprint and shoe alignment

---
class: inverse
# Miranda

---
class: primary
# More Surprises

- Class confusion matrix is informative for models from two weeks ago, but very strange for most recent models

---
class: primary
# Image Quantity

- Might be an issue of relative quantities between classes
- May combine pentagon and hexagon
- May also augment classes proportionally
<img src = "images/miranda/18-10-1/ImageQuantity.png" width="70%"/>

---
class: inverse
# Issues

---
class: secondary

- [Issues!!](https://github.com/CSAFE-ISU/slides/issues)
- Two issues down, two to go.